# Leveraging Partial Symmetry for Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2401.00167 · HTML: https://mlsanity.com/paper/2401.00167/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2023.

## Built on by (most cited first, 11 of 11)

- [Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection](https://mlsanity.com/paper/2408.08902/) (2024)
- [Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks](https://mlsanity.com/paper/2407.08164/) (2024)
- [RedChronos: A Large Language Model-Based Log Analysis System for Insider Threat Detection in Enterprises](https://mlsanity.com/paper/2503.02702/) (2025)
- [SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding](https://mlsanity.com/paper/2502.06440/) (2025)
- [PEnGUiN: Partially Equivariant Graph NeUral Networks for Sample Efficient MARL](https://mlsanity.com/paper/2503.15615/) (2025)
- [Spatial-Temporal Transformer with Curriculum Learning for EEG-Based Emotion Recognition](https://mlsanity.com/paper/2507.14698/) (2025)
- [Solving the Min-Max Multiple Traveling Salesmen Problem via Learning-Based Path Generation and Optimal Splitting](https://mlsanity.com/paper/2508.17087/) (2025)
- [Equivariant Multi-agent Reinforcement Learning for Multimodal Vehicle-to-Infrastructure Systems](https://mlsanity.com/paper/2604.06914/) (2026)
- [Symmetry-Guided Multi-Agent Inverse Reinforcement Learning](https://mlsanity.com/paper/2509.08257/) (2025)
- [Reinforcement Learning Using known Invariances](https://mlsanity.com/paper/2511.03473/) (2025)
- [A Unified Knowledge Embedded Reinforcement Learning-based Framework for Generalized Capacitated Vehicle Routing Problems](https://mlsanity.com/paper/2605.14416/) (2026)

## Abstract (arXiv)

Incorporating symmetry as an inductive bias into multi-agent reinforcement learning (MARL) has led to improvements in generalization, data efficiency, and physical consistency. While prior research has succeeded in using perfect symmetry prior, the realm of partial symmetry in the multi-agent domain remains unexplored. To fill in this gap, we introduce the partially symmetric Markov game, a new subclass of the Markov game. We then theoretically show that the performance error introduced by utilizing symmetry in MARL is bounded, implying that the symmetry prior can still be useful in MARL even in partial symmetry situations. Motivated by this insight, we propose the Partial Symmetry Exploitation (PSE) framework that is able to adaptively incorporate symmetry prior in MARL under different symmetry-breaking conditions. Specifically, by adaptively adjusting the exploitation of symmetry, our framework is able to achieve superior sample efficiency and overall performance of MARL algorithms. Extensive experiments are conducted to demonstrate the superior performance of the proposed framework over baselines. Finally, we implement the proposed framework in real-world multi-robot testbed to show its superiority.